University of Oulu

Kollias, D., Tzirakis, P., Nicolaou, M.A. et al. Int J Comput Vis (2019) 127: 907. https://doi.org/10.1007/s11263-019-01158-4

Deep affect prediction in-the-wild : aff-wild database and challenge, deep architectures, and beyond

Saved in:
Author: Kollias, Dimitrios1; Tzirakis, Panagiotis1; Nicolaou, Mihalis A.1,2;
Organizations: 1Queens Gate, London SW7 2AZ, UK
2Department of Computing, Goldsmiths University of London, London SE14 6NW, UK
3Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland
4Department of Computer Science, Middlesex University of London, London NW4 4BT, UK
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 3 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2019060618728
Language: English
Published: Springer Nature, 2019
Publish Date: 2019-06-06
Description:

Abstract

Automatic understanding of human affect using visual signals is of great importance in everyday human–machine interactions. Appraising human emotional states, behaviors and reactions displayed in real-world settings, can be accomplished using latent continuous dimensions (e.g., the circumplex model of affect). Valence (i.e., how positive or negative is an emotion) and arousal (i.e., power of the activation of the emotion) constitute popular and effective representations for affect. Nevertheless, the majority of collected datasets this far, although containing naturalistic emotional states, have been captured in highly controlled recording conditions. In this paper, we introduce the Aff-Wild benchmark for training and evaluating affect recognition algorithms. We also report on the results of the First Affect-in-the-wild Challenge (Aff-Wild Challenge) that was recently organized in conjunction with CVPR 2017 on the Aff-Wild database, and was the first ever challenge on the estimation of valence and arousal in-the-wild. Furthermore, we design and extensively train an end-to-end deep neural architecture which performs prediction of continuous emotion dimensions based on visual cues. The proposed deep learning architecture, AffWildNet, includes convolutional and recurrent neural network layers, exploiting the invariant properties of convolutional features, while also modeling temporal dynamics that arise in human behavior via the recurrent layers. The AffWildNet produced state-of-the-art results on the Aff-Wild Challenge. We then exploit the AffWild database for learning features, which can be used as priors for achieving best performances both for dimensional, as well as categorical emotion recognition, using the RECOLA, AFEW-VA and EmotiW 2017 datasets, compared to all other methods designed for the same goal. The database and emotion recognition models are available at http://ibug.doc.ic.ac.uk/resources/first-affect-wild-challenge.

see all

Series: International journal of computer vision
ISSN: 0920-5691
ISSN-E: 1573-1405
ISSN-L: 0920-5691
Volume: 127
Issue: 6-7
Pages: 907 - 929
DOI: 10.1007/s11263-019-01158-4
OADOI: https://oadoi.org/10.1007/s11263-019-01158-4
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
Subjects:
Copyright information: © The Author(s) 2019. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
  https://creativecommons.org/licenses/by/4.0/